In order to improve the accuracy of voltage sag source identification

a voltage sag source identification method based on the improved whale optimization algorithm(IWOA) optimized support vector machine(SVM) is proposed.Firstly

by using S variable losses to process the voltage signal

16 feature quantities are obtained for voltage sag source identification.Secondly

multiple mea-sures such as population chaos initialization

nonlinear convergence factor

and Cauchy mutation are adopted to improve the whale optimization algorithm

resulting in the IWOA algorithm with better convergence performance.The IWOA algorithm is used to search for the optimal parameter values of SVM

and a voltage sag source identification model based on IWOA-SVM is constructed.Six different categories of voltage sag disturbance signals are used for example analysis.The results show that the recognition accuracy of the IWOA-SVM model is as high as 98.33%

and the recognition effect is better than other methods

verifying the effectiveness of the proposed voltage sag source identification method.